Artificial Neural Network-Based Control of Switched Reluctance Motor for Torque Ripple Reduction

Abstract

Switched reluctance motor is acquiring major attention because of its simple design, economic development, and reduced dependability. These attributes make switched reluctance motors superior to other variable speed machines. The major challenge associated with the development of a switched reluctance motor is its high torque ripple. Torque ripple produces noise and vibration, resulting in degradation of its performance. Various techniques are developed to cope with torque ripples. Practically, there exists not a single mature technique for the minimization of torque ripples in switched reluctance motors. In this research, a switched reluctance motor is modelled and analysed. Its speed and current control are implemented through artificial neural networks. Artificial neural network is found to be a promising technique as compared with other techniques because of its accuracy, reduced complexity, stability, and generalization. The Levenberg–Marquardt algorithm is utilized in artificial neural networks due to its fast and stable convergence for training and testing. It is found from research that artificial neural network-based improved control shows better performance of the switched reluctance motor. Realization of this technique is further validated from its mean square error analysis. Operating parameters of the switched reluctance motor are improved significantly. Simulation environment is created in Matlab/Simulink.

Online Current Spikes Suppression Strategy Research of Switched Reluctance Motors Based on Hybrid Torque Sharing Function

“…The literature [8] constructed the turn-on angle selection function by inductance curve characteristics to track the reference torque and suppress the current spikes. In literature [9], the TSF parameters were optimized by torque feedback to reduce the torque ripple effectively, but the current spikes rose; the literature [10] used neural network with Levenberg-Marquardt algorithm to achieve speed and current control. The experiments showed that this method can improve the torque ripple quickly and the current spikes of phase commutation were reduced by about 20% in SRM control process, but a large amount of preliminary experimental data must be needed for neural network training.…”

Novel Design and Simulation of Fuzzy Controller for Turn-On & Turn-Off Angle in Coordination with SRM Speed Control for Electric Vehicles

“…Speed control of SRM is discussed by using PI controller with constant α and β and it will take more time to settle its rated speed [26]. The torque ripple effect of SRM is reduced by using artificial neural networks with constant angles (α, β) in this method, rated speeds can settle with less time [27]. The effectiveness of SRM as well as various speed control techniques such as PI and fuzzy are reviewed in [28].…”